Published June 27, 2023
| Version v1
Preprint
Open
Audio-Visual Dataset and Method for Anomaly Detection in Traffic Videos
Creators
- 1. DIGIT, Department of Electrical and Computer Engineering, Aarhus University, Denmark
- 2. Greenroads Ltd., TAKEOFF, University of Malta, Malta
- 3. Department of Computer Engineering, University of Malta, Malta
- 4. Fondazione Bruno Kessler, Trento, Italy & University of Trento, Trento, Italy
- 5. Fondazione Bruno Kessler, Trento, Italy
Description
We introduce the first audio-visual dataset for traffic anomaly detection taken from real-world scenes, called MAVAD, with a diverse range of weather and illumination conditions. In addition, we propose a novel method named AVACA that combines visual and audio features extracted from video sequences by means of cross-attention to detect anomalies. We demonstrate that the addition of audio improves the performance of AVACA by up to 5.2%. We also evaluate the impact of image anonymization, showing only a minor decrease in performance averaging at 1.7%.
Files
Leporowski_etal_MAVAD_2023.pdf
Files
(1.3 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:73a39a58f949c81a6b48b096fdd30f23
|
1.3 MB | Preview Download |
Additional details
Related works
- Is supplemented by
- 10.5281/zenodo.7950008 (DOI)